INDEX

Explanations

references to individuals within a legal or educational context

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Tycoon

-0.56

 veget

-0.56

 virginity

-0.54

 partying

-0.53

 raping

-0.53

 fitt

-0.53

animate

-0.49

 prostitutes

-0.49

enery

-0.49

 predators

-0.49

POSITIVE LOGITS

 publication

0.69

 editorial

0.67

 reader

0.65

ascript

0.65

 journalistic

0.64

 Editorial

0.62

 explanatory

0.62

 editor

0.61

 methodological

0.60

 Publication

0.59

Activations Density 7.965%

references to individuals within a legal or educational context

No Comments

No Known Activations